Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1298 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0003

Data Index: 461816 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0568. Min Act: -0.0003

Data Index: 839046 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0554. Min Act: -0.0003

Data Index: 177138 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0549. Min Act: -0.0004

Data Index: 948276 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0532. Min Act: -0.0003

Data Index: 536371 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0511. Min Act: -0.0003

Data Index: 520948 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0508. Min Act: -0.0003

Data Index: 38392 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0514. Min Act: -0.0003

Data Index: 340017 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0513. Min Act: -0.0004

Data Index: 1122587 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1281541 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1072800 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0493. Min Act: -0.0003

Data Index: 296949 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0487. Min Act: -0.0002

Data Index: 955300 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1329119 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0494. Min Act: -0.0004

Data Index: 498020 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0480. Min Act: -0.0003

Data Index: 901838 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1058399 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0487. Min Act: -0.0003

Data Index: 1249821 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0484. Min Act: -0.0003

Data Index: 192358 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0479. Min Act: -0.0004

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 287